CodeQwen1.5-7B-Chat_Finetuned_dataset_size_52_epochs_10_2024-06-08_21-43-43 – AI Model by vdavidr | AlphaNeural AI

You can deploy this model and start earning money today!

vdavidr/
CodeQwen1.5-7B-Chat_Finetuned_dataset_size_52_epochs_10_2024-06-08_21-43-43

like

0

generated_from_trainer

Qwen/CodeQwen1.5-7B-Chat

Views

No views yet

CodeQwen1.5-7B-Chat_Finetuned_dataset_size_52_epochs_10_2024-06-08_21-43-43

This model is a fine-tuned version of Qwen/CodeQwen1.5-7B-Chat on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.7870
Accuracy: 0.073
Chrf: 0.787
Bleu: 0.671
Sacrebleu: 0.7
Rouge1: 0.766
Rouge2: 0.57
Rougel: 0.698
Rougelsum: 0.752
Meteor: 0.577

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.001
train_batch_size: 1
eval_batch_size: 1
seed: 3407
distributed_type: multi-GPU
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-06
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 52
training_steps: 520
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Chrf	Bleu	Sacrebleu	Rouge1	Rouge2	Rougel	Rougelsum	Meteor
0.0792	1.0	52	0.6372	0.074	0.809	0.718	0.7	0.784	0.598	0.725	0.771	0.669
0.0236	2.0	104	0.8347	0.074	0.81	0.659	0.7	0.705	0.509	0.666	0.688	0.518
0.0294	3.0	156	0.7025	0.075	0.801	0.693	0.7	0.763	0.572	0.705	0.75	0.598
0.117	4.0	208	0.9071	0.091	0.786	0.669	0.7	0.752	0.562	0.691	0.735	0.601
0.9827	5.0	260	7.8455	0.044	0.015	0.0	0.0	0.034	0.003	0.028	0.031	0.038
0.2169	6.0	312	1.2152	0.075	0.685	0.512	0.5	0.64	0.369	0.554	0.624	0.49
0.127	7.0	364	1.4136	0.083	0.692	0.527	0.5	0.634	0.367	0.534	0.617	0.504
0.1917	8.0	416	0.9597	0.073	0.755	0.619	0.6	0.707	0.48	0.631	0.696	0.549
0.0853	9.0	468	0.8261	0.073	0.784	0.665	0.7	0.756	0.558	0.689	0.743	0.564
0.0365	10.0	520	0.7870	0.073	0.787	0.671	0.7	0.766	0.57	0.698	0.752	0.577

Framework versions

PEFT 0.7.1
Transformers 4.37.0
Pytorch 2.2.0+cu121
Datasets 2.19.2
Tokenizers 0.15.2